Convolutional Neural Networks

Project: Write an Algorithm for a Dog Identification App


In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!

Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.

In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.

Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.

The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.


Why We're Here

In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

Sample Dog Output

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!

The Road Ahead

We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.

  • Step 0: Import Datasets
  • Step 1: Detect Humans
  • Step 2: Detect Dogs
  • Step 3: Create a CNN to Classify Dog Breeds (from Scratch)
  • Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)
  • Step 5: Write your Algorithm
  • Step 6: Test Your Algorithm

Step 0: Import Datasets

Make sure that you've downloaded the required human and dog datasets:

Note: if you are using the Udacity workspace, you DO NOT need to re-download these - they can be found in the /data folder as noted in the cell below.

  • Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dog_images.

  • Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.

Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.

In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.

In [2]:
import numpy as np
from glob import glob
from pandas import DataFrame

# load filenames for human and dog images
human_files = np.array(glob("/data/lfw/*/*"))
dog_files = np.array(glob("/data/dog_images/*/*/*"))

# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
There are 13233 total human images.
There are 8351 total dog images.

Step 1: Detect Humans

In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.

OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.

In [3]:
import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# find faces in image
faces = face_cascade.detectMultiScale(gray)

# print number of faces detected in the image
print('Number of faces detected:', len(faces))

# get bounding box for each detected face
for (x,y,w,h) in faces:
    # add bounding box to color image
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Number of faces detected: 1

Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.

In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.

Write a Human Face Detector

We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.

In [4]:
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0

(IMPLEMENTATION) Assess the Human Face Detector

Question 1: Use the code cell below to test the performance of the face_detector function.

  • What percentage of the first 100 images in human_files have a detected human face?
  • What percentage of the first 100 images in dog_files have a detected human face?

Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.

Answer: human: 98% dog: 98%

In [5]:
from tqdm import tqdm

human_files_short = human_files[:100]
dog_files_short = dog_files[:100]

#-#-# Do NOT modify the code above this line. #-#-#

## TODO: Test the performance of the face_detector algorithm 
human_running_loss = 0
human_loss = 0
dog_running_loss = 0
dog_loss = 0

#create arrays that will hold string results (true/false)
human_result = ["string"] * len(human_files_short)
dog_result = ["string"] * len(dog_files_short)

for i in range(len(human_files_short)):
    human_result[i] = face_detector(human_files_short[i])
    if human_result[i] == False:
        human_loss = 1
    human_running_loss += human_loss
    dog_result[i] = face_detector(dog_files_short[i])
    if dog_result[i] == False:
        dog_loss = 1
    dog_running_loss += dog_loss

human_accuracy = human_result.count(True) / len(human_files_short)
dog_accuracy = human_result.count(True) / len(human_files_short)

print("Prediction accuracy - human: {:.3f}".format(human_accuracy))
print("Prediction accuracy - dog: {:.3f}".format(dog_accuracy))
## on the images in human_files_short and dog_files_short.
Prediction accuracy - human: 0.980
Prediction accuracy - dog: 0.980

We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [ ]:
### (Optional) 
### TODO: Test performance of anotherface detection algorithm.
### Feel free to use as many code cells as needed.

Step 2: Detect Dogs

In this section, we use a pre-trained model to detect dogs in images.

Obtain Pre-trained VGG-16 Model

The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.

In [6]:
import torch
import torchvision.models as models

# define VGG16 model
VGG16 = models.vgg16(pretrained=True)

# check if CUDA is available
use_cuda = torch.cuda.is_available()

# move model to GPU if CUDA is available
if use_cuda:
    VGG16 = VGG16.cuda()
Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to /root/.torch/models/vgg16-397923af.pth
100%|██████████| 553433881/553433881 [00:42<00:00, 13026860.81it/s]

Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.

(IMPLEMENTATION) Making Predictions with a Pre-trained Model

In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.

Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.

In [7]:
#import helper
from PIL import Image
#ImageFile.LOAD_TRUNCATED_IMAGES = True
from torchvision import datasets, transforms


#added
import os
from pandas import DataFrame
import torch.nn as nn
import torch.optim as optim
import torchvision
import torch

def VGG16_predict(img_path):
    '''
    Use pre-trained VGG-16 model to obtain index corresponding to 
    predicted ImageNet class for image at specified path
    
    Args:
        img_path: path to an image
        
    Returns:
        Index corresponding to VGG-16 model's prediction
    '''
    #'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg'
    
    #open the img
    img = Image.open(img_path)
    
    
    ## TODO: Complete the function.
    transform = transforms.Compose([transforms.RandomRotation(30),
                                    transforms.RandomResizedCrop(224),
                                    transforms.RandomHorizontalFlip(),
                                       transforms.ToTensor()]) 
    
    image = transform(img).unsqueeze_(0)
    if use_cuda:
       image = image.cuda()
    VGG16.eval() # to put in eval mode as we are only doing inference
    
    output = torch.argmax(VGG16(image)).item()
   # output2 = VGG16(image)   
    return output # predicted class index

#VGG16_predict('/data/dog_images/train/001.Affenpinscher/Affenpinscher_00001.jpg')

(IMPLEMENTATION) Write a Dog Detector

While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).

Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).

In [8]:
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
    ## TODO: Complete the function.
    output = VGG16_predict(img_path)
    if output > 150 and output < 269:
        output2 = True
    else:
        output2 = False
    return output2 # true/false

(IMPLEMENTATION) Assess the Dog Detector

Question 2: Use the code cell below to test the performance of your dog_detector function.

  • What percentage of the images in human_files_short have a detected dog?
  • What percentage of the images in dog_files_short have a detected dog?

Answer: 2% in both human and dog

In [8]:
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.

human_running_loss = 0
human_loss = 0
dog_running_loss = 0
dog_loss = 0
human_result = ["string"] * len(human_files_short)
dog_result = ["string"] * len(dog_files_short)

for i in range(len(human_files_short)):
    human_result[i] = dog_detector(human_files_short[i])
    if human_result[i] == False:
        human_loss = 1
    human_running_loss += human_loss
    dog_result[i] = dog_detector(dog_files_short[i])
    if dog_result[i] == False:
        dog_loss = 1
    dog_running_loss += dog_loss

human_accuracy = human_result.count(True) / len(human_files_short)
dog_accuracy = human_result.count(True) / len(human_files_short)

print("Prediction accuracy - human: {:.6f}".format(human_accuracy))
print("Prediction accuracy - dog: {:.6f}".format(dog_accuracy))
Prediction accuracy - human: 0.020000
Prediction accuracy - dog: 0.020000

We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [ ]:
### (Optional) 
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.

Step 3: Create a CNN to Classify Dog Breeds (from Scratch)

Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.

We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.

Brittany Welsh Springer Spaniel

It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).

Curly-Coated Retriever American Water Spaniel

Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.

Yellow Labrador Chocolate Labrador Black Labrador

We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.

Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dog_images/train, dog_images/valid, and dog_images/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!

In [9]:
import os
from torchvision import datasets
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

### TODO: Write data loaders for training, validation, and test sets

data_dir = '/data/dog_images/'
train_dir = os.path.join(data_dir, 'train')
test_dir = os.path.join(data_dir, 'test')
valid_dir = os.path.join(data_dir, 'valid')

## Specify appropriate transforms, and batch_sizes

data_transform = transforms.Compose([transforms.RandomRotation(30),
                                     transforms.RandomResizedCrop(256),
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor()])
    
train_data = datasets.ImageFolder(train_dir, transform = data_transform)
test_data = datasets.ImageFolder(test_dir, transform = data_transform)
valid_data = datasets.ImageFolder(valid_dir, transform = data_transform)

batch_size = 20
num_workers = 0

#train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#valid_loader = torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)

loaders_scratch={'train':torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
                 'test':torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
                 'valid':torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)}

Question 3: Describe your chosen procedure for preprocessing the data.

  • How does your code resize the images (by cropping, stretching, etc)? What size did you pick for the input tensor, and why?
  • Did you decide to augment the dataset? If so, how (through translations, flips, rotations, etc)? If not, why not?

Answer: Resizing done by cropping. The input tensor size is 32 - in line with CNN below required inputs Yes - augmented the dataset with rotations and horizontal flips.

(IMPLEMENTATION) Model Architecture

Create a CNN to classify dog breed. Use the template in the code cell below.

In [10]:
import torch.nn as nn
import torch.nn.functional as F

# define the CNN architecture
class Net(nn.Module):
    ### TODO: choose an architecture, and complete the class
    def __init__(self):
        super(Net, self).__init__()
        ## Define layers of a CNN
        # convolutional layer (sees 256x256x3 image tensor)
        self.conv1 = nn.Conv2d(3, 8, 3, padding=1)
        # convolutional layer (sees 128x128x3 image tensor)
        self.conv2 = nn.Conv2d(8, 16, 3, padding=1)
        # convolutional layer (sees 64x64x16 tensor)
        self.conv3 = nn.Conv2d(16, 32, 3, padding=1)
        # convolutional layer (sees 32x32x32 tensor)
        self.conv4 = nn.Conv2d(32, 64, 3, padding=1)
        # convolutional layer (sees 16x16x64 tensor)
        self.conv5 = nn.Conv2d(64, 128, 3, padding=1)
        # convolutional layer (sees 8x8x128 tensor)
        self.conv6 = nn.Conv2d(128, 256, 3, padding=1)
        # max pooling layer
        self.pool = nn.MaxPool2d(2, 2)
        # linear layer (256 * 4 * 4 -> 500)
        self.fc1 = nn.Linear(256 * 4 * 4, 2000)
        # linear layer (2000 -> 500)
        self.fc2 = nn.Linear(2000, 500)
        #linear layer (500 -> 133)
        self.fc3 = nn.Linear(500, 133)
        # dropout layer (p=0.25)
        self.dropout = nn.Dropout(0.25)
        
    def forward(self, x):
        ## Define forward behavior
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.pool(F.relu(self.conv3(x)))
        x = self.pool(F.relu(self.conv4(x)))
        x = self.pool(F.relu(self.conv5(x)))
        x = self.pool(F.relu(self.conv6(x)))
        # flatten image input
        x = x.view(-1, 256 * 4 * 4)
        # add dropout layer
        x = self.dropout(x)
        # add 1st hidden layer, with relu activation function
        x = F.relu(self.fc1(x))
        # add dropout layer
        x = self.dropout(x)
        # add 2nd hidden layer, with relu activation function
        x = self.fc2(x)
        # add dropout layer
        x = self.dropout(x)
        # add 2nd hidden layer, with relu activation function
        x = self.fc3(x)
        return x

#-#-# You so NOT have to modify the code below this line. #-#-#

# instantiate the CNN
model_scratch = Net()

# move tensors to GPU if CUDA is available
if use_cuda:
    model_scratch.cuda()

Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.

Answer: Based on CIFAR structure to start with:

Input: 256x256 pixel by 3 (for RGB). Tried to get as close to actual dog picture sizes - which are around 400+ pixels

Layer 1 Convolutional layer: takes in an input of 3 (RGB) and want the output to be 8. Kernel size is 3 with padding of 1

Maxpool 1: turns the 256 by 256 pixel image into a 128 x 128 image, with a depth of 8

Layer 2 Convolutional layer: takes the input from maxpool 1 and turns it into an output of 16. Kernel size and padding unchanged

Maxpool 2: turns the 128 by 128 pixel image into an 64 x 64 image, with a depth of 16

Layer 3 Convolutional layer: takes in an input of 3 (RGB) and want the output to be 32. Kernel size is 3 with padding of 1

Maxpool 3: turns the 64 by 64 pixel image into a 32 x 32 image, with a depth of 32

Layer 4 Convolutional layer: takes the input from maxpool 3 and turns it into an output of 64. Kernel size and padding unchanged

Maxpool 4: turns the 32 by 32 pixel image into an 16 x 16 image, with a depth of 64

Layer 5 Convolutional layer: takes the input from maxpool 4 and turns it into an output of 128. Kernel size and padding unchanged.

Maxpool 5: turns the 16 by 16 image into a 8 by 8 image, depth stays at 128.

Layer 6 Convolutional layer: takes the input from maxpool 5 and turns it into an output of 256. Kernel size and padding unchanged.

Maxpool 6: turns the 8 by 8 image into a 8 by 8 image, depth stays at 256.

Now the output is flattened so we can put it into a fully connected layer. Note that the dimension of the first fully connected layer is the depth from layer 3 convolutional layer (64) multiplied by 4 x 4

Dropout layers interleaved before and after the 1st fully connected layer to discourage overfitting.

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.

In [11]:
import torch.optim as optim

### TODO: select loss function
criterion_scratch = nn.CrossEntropyLoss()

### TODO: select optimizer
optimizer_scratch = optim.SGD(model_scratch.parameters(), lr = 0.01)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.

In [12]:
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
    """returns trained model"""
    # initialize tracker for minimum validation loss
    valid_loss_min = np.Inf 
    
    for epoch in range(1, n_epochs+1):
        # initialize variables to monitor training and validation loss
        train_loss = 0.0
        valid_loss = 0.0
        
        ###################
        # train the model #
        ###################
        model.train()
        for batch_idx, (data, target) in enumerate(loaders['train']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## find the loss and update the model parameters accordingly
            #clear gradients
            optimizer_scratch.zero_grad()
            #forward pass
            output = model_scratch(data)
            # calculate the batch loss
            loss = criterion(output, target)
            #backward pass
            loss.backward()
            #update parameters
            optimizer_scratch.step()
            #train_loss updated
            #train_loss += loss.item()*data.size(0)
            ## record the average training loss, using something like
            train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
            
        ######################    
        # validate the model #
        ######################
        model.eval()
        for batch_idx, (data, target) in enumerate(loaders['valid']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## update the average validation loss
            valid_loss = valid_loss + ((1 / (batch_idx + 1)) * (loss.data - valid_loss))
            
        # print training/validation statistics 
        print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
            epoch, 
            train_loss,
            valid_loss
            ))
        
        ## TODO: save the model if validation loss has decreased
        if valid_loss <= valid_loss_min:
            print('Validation loss decreased --> ',
                 'Saving model ...'.format(valid_loss_min, 
                                           valid_loss))
            torch.save(model_scratch.state_dict(), 'model_scratch.pt')
            valid_loss_min = valid_loss
            
            
    # return trained model
    return model


# train the model
model_scratch = train(100, loaders_scratch, model_scratch, optimizer_scratch, 
                      criterion_scratch, use_cuda, 'model_scratch.pt')

# load the model that got the best validation accuracy
model_scratch.load_state_dict(torch.load('model_scratch.pt'))
Epoch: 1 	Training Loss: 4.889671 	Validation Loss: 4.894041
Validation loss decreased -->  Saving model ...
Epoch: 2 	Training Loss: 4.887605 	Validation Loss: 4.879059
Validation loss decreased -->  Saving model ...
Epoch: 3 	Training Loss: 4.885661 	Validation Loss: 4.887676
Epoch: 4 	Training Loss: 4.883804 	Validation Loss: 4.868116
Validation loss decreased -->  Saving model ...
Epoch: 5 	Training Loss: 4.881873 	Validation Loss: 4.875222
Epoch: 6 	Training Loss: 4.880163 	Validation Loss: 4.847722
Validation loss decreased -->  Saving model ...
Epoch: 7 	Training Loss: 4.878615 	Validation Loss: 4.872848
Epoch: 8 	Training Loss: 4.876763 	Validation Loss: 4.890670
Epoch: 9 	Training Loss: 4.874315 	Validation Loss: 4.868876
Epoch: 10 	Training Loss: 4.872071 	Validation Loss: 4.814420
Validation loss decreased -->  Saving model ...
Epoch: 11 	Training Loss: 4.868366 	Validation Loss: 4.818440
Epoch: 12 	Training Loss: 4.866500 	Validation Loss: 4.848583
Epoch: 13 	Training Loss: 4.865384 	Validation Loss: 4.770242
Validation loss decreased -->  Saving model ...
Epoch: 14 	Training Loss: 4.865047 	Validation Loss: 4.888305
Epoch: 15 	Training Loss: 4.864350 	Validation Loss: 4.877158
Epoch: 16 	Training Loss: 4.863732 	Validation Loss: 4.948503
Epoch: 17 	Training Loss: 4.863716 	Validation Loss: 4.786833
Epoch: 18 	Training Loss: 4.862538 	Validation Loss: 4.915305
Epoch: 19 	Training Loss: 4.862140 	Validation Loss: 4.924053
Epoch: 20 	Training Loss: 4.862723 	Validation Loss: 4.936837
Epoch: 21 	Training Loss: 4.860741 	Validation Loss: 4.949535
Epoch: 22 	Training Loss: 4.859043 	Validation Loss: 4.803197
Epoch: 23 	Training Loss: 4.856683 	Validation Loss: 4.874115
Epoch: 24 	Training Loss: 4.855645 	Validation Loss: 4.919250
Epoch: 25 	Training Loss: 4.850353 	Validation Loss: 4.907844
Epoch: 26 	Training Loss: 4.840813 	Validation Loss: 4.913148
Epoch: 27 	Training Loss: 4.830233 	Validation Loss: 4.838242
Epoch: 28 	Training Loss: 4.817960 	Validation Loss: 4.874831
Epoch: 29 	Training Loss: 4.798238 	Validation Loss: 4.700485
Validation loss decreased -->  Saving model ...
Epoch: 30 	Training Loss: 4.771164 	Validation Loss: 4.801682
Epoch: 31 	Training Loss: 4.759251 	Validation Loss: 4.700748
Epoch: 32 	Training Loss: 4.732022 	Validation Loss: 4.763148
Epoch: 33 	Training Loss: 4.709912 	Validation Loss: 5.018816
Epoch: 34 	Training Loss: 4.709786 	Validation Loss: 4.777723
Epoch: 35 	Training Loss: 4.700737 	Validation Loss: 4.816222
Epoch: 36 	Training Loss: 4.680270 	Validation Loss: 4.590652
Validation loss decreased -->  Saving model ...
Epoch: 37 	Training Loss: 4.668939 	Validation Loss: 4.897635
Epoch: 38 	Training Loss: 4.660129 	Validation Loss: 4.692218
Epoch: 39 	Training Loss: 4.654623 	Validation Loss: 4.787302
Epoch: 40 	Training Loss: 4.637720 	Validation Loss: 4.497639
Validation loss decreased -->  Saving model ...
Epoch: 41 	Training Loss: 4.629750 	Validation Loss: 4.408434
Validation loss decreased -->  Saving model ...
Epoch: 42 	Training Loss: 4.611619 	Validation Loss: 4.606871
Epoch: 43 	Training Loss: 4.603171 	Validation Loss: 4.729120
Epoch: 44 	Training Loss: 4.591116 	Validation Loss: 4.716448
Epoch: 45 	Training Loss: 4.581489 	Validation Loss: 4.557994
Epoch: 46 	Training Loss: 4.566142 	Validation Loss: 4.466920
Epoch: 47 	Training Loss: 4.559204 	Validation Loss: 4.387526
Validation loss decreased -->  Saving model ...
Epoch: 48 	Training Loss: 4.544966 	Validation Loss: 4.470740
Epoch: 49 	Training Loss: 4.519252 	Validation Loss: 4.425155
Epoch: 50 	Training Loss: 4.487895 	Validation Loss: 4.511473
Epoch: 51 	Training Loss: 4.465119 	Validation Loss: 4.413821
Epoch: 52 	Training Loss: 4.457177 	Validation Loss: 4.596800
Epoch: 53 	Training Loss: 4.443645 	Validation Loss: 4.603001
Epoch: 54 	Training Loss: 4.419352 	Validation Loss: 4.327627
Validation loss decreased -->  Saving model ...
Epoch: 55 	Training Loss: 4.401467 	Validation Loss: 4.581918
Epoch: 56 	Training Loss: 4.401690 	Validation Loss: 4.573373
Epoch: 57 	Training Loss: 4.375962 	Validation Loss: 4.001932
Validation loss decreased -->  Saving model ...
Epoch: 58 	Training Loss: 4.359319 	Validation Loss: 4.184343
Epoch: 59 	Training Loss: 4.347495 	Validation Loss: 4.573453
Epoch: 60 	Training Loss: 4.332969 	Validation Loss: 3.920579
Validation loss decreased -->  Saving model ...
Epoch: 61 	Training Loss: 4.318772 	Validation Loss: 3.886937
Validation loss decreased -->  Saving model ...
Epoch: 62 	Training Loss: 4.291640 	Validation Loss: 4.733643
Epoch: 63 	Training Loss: 4.275694 	Validation Loss: 4.114819
Epoch: 64 	Training Loss: 4.260786 	Validation Loss: 4.162770
Epoch: 65 	Training Loss: 4.269182 	Validation Loss: 3.931281
Epoch: 66 	Training Loss: 4.236396 	Validation Loss: 4.399980
Epoch: 67 	Training Loss: 4.225345 	Validation Loss: 4.185336
Epoch: 68 	Training Loss: 4.211531 	Validation Loss: 3.958531
Epoch: 69 	Training Loss: 4.192315 	Validation Loss: 4.154141
Epoch: 70 	Training Loss: 4.182484 	Validation Loss: 4.320986
Epoch: 71 	Training Loss: 4.175883 	Validation Loss: 4.299991
Epoch: 72 	Training Loss: 4.146366 	Validation Loss: 4.025466
Epoch: 73 	Training Loss: 4.145053 	Validation Loss: 4.110370
Epoch: 74 	Training Loss: 4.139591 	Validation Loss: 4.143506
Epoch: 75 	Training Loss: 4.116834 	Validation Loss: 3.981914
Epoch: 76 	Training Loss: 4.110453 	Validation Loss: 4.176555
Epoch: 77 	Training Loss: 4.093865 	Validation Loss: 4.512237
Epoch: 78 	Training Loss: 4.092728 	Validation Loss: 4.047663
Epoch: 79 	Training Loss: 4.060049 	Validation Loss: 3.795833
Validation loss decreased -->  Saving model ...
Epoch: 80 	Training Loss: 4.027582 	Validation Loss: 4.197488
Epoch: 81 	Training Loss: 4.025302 	Validation Loss: 3.740667
Validation loss decreased -->  Saving model ...
Epoch: 82 	Training Loss: 4.014287 	Validation Loss: 3.574548
Validation loss decreased -->  Saving model ...
Epoch: 83 	Training Loss: 3.992476 	Validation Loss: 3.771552
Epoch: 84 	Training Loss: 3.965247 	Validation Loss: 4.062011
Epoch: 85 	Training Loss: 3.949701 	Validation Loss: 3.855123
Epoch: 86 	Training Loss: 3.941062 	Validation Loss: 4.330994
Epoch: 87 	Training Loss: 3.926635 	Validation Loss: 3.735844
Epoch: 88 	Training Loss: 3.916852 	Validation Loss: 3.893792
Epoch: 89 	Training Loss: 3.889426 	Validation Loss: 3.477181
Validation loss decreased -->  Saving model ...
Epoch: 90 	Training Loss: 3.889566 	Validation Loss: 3.738710
Epoch: 91 	Training Loss: 3.871783 	Validation Loss: 3.758698
Epoch: 92 	Training Loss: 3.847363 	Validation Loss: 3.801971
Epoch: 93 	Training Loss: 3.853780 	Validation Loss: 3.609231
Epoch: 94 	Training Loss: 3.824565 	Validation Loss: 3.785627
Epoch: 95 	Training Loss: 3.810672 	Validation Loss: 3.487833
Epoch: 96 	Training Loss: 3.795724 	Validation Loss: 3.861529
Epoch: 97 	Training Loss: 3.775717 	Validation Loss: 4.413661
Epoch: 98 	Training Loss: 3.758195 	Validation Loss: 3.744834
Epoch: 99 	Training Loss: 3.720472 	Validation Loss: 3.419942
Validation loss decreased -->  Saving model ...
Epoch: 100 	Training Loss: 3.714748 	Validation Loss: 4.383325

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.

In [13]:
def test(loaders, model, criterion, use_cuda):

    # monitor test loss and accuracy
    test_loss = 0.
    correct = 0.
    total = 0.

    model.eval()
    for batch_idx, (data, target) in enumerate(loaders['test']):
        # move to GPU
        if use_cuda:
            data, target = data.cuda(), target.cuda()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = model(data)
        # calculate the loss
        loss = criterion(output, target)
        # update average test loss 
        test_loss = test_loss + ((1 / (batch_idx + 1)) * (loss.data - test_loss))
        # convert output probabilities to predicted class
        pred = output.data.max(1, keepdim=True)[1]
        # compare predictions to true label
        correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
        total += data.size(0)
            
    print('Test Loss: {:.6f}\n'.format(test_loss))

    print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))

# call test function    
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
Test Loss: 3.965917


Test Accuracy: 11% (95/836)

Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)

You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).

If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.

In [10]:
## TODO: Specify data loaders

import os
from torchvision import datasets
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

### TODO: Write data loaders for training, validation, and test sets

data_dir = '/data/dog_images/'
train_dir = os.path.join(data_dir, 'train')
test_dir = os.path.join(data_dir, 'test')
valid_dir = os.path.join(data_dir, 'valid')

## Specify appropriate transforms, and batch_sizes

data_transform = transforms.Compose([transforms.RandomRotation(30),
                                     transforms.RandomResizedCrop(224), #need this for VGG16!
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor()])
    
train_data = datasets.ImageFolder(train_dir, transform = data_transform)
test_data = datasets.ImageFolder(test_dir, transform = data_transform)
valid_data = datasets.ImageFolder(valid_dir, transform = data_transform)

batch_size = 20
num_workers = 0

#train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)
#valid_loader = torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)

loaders_transfer={'train':torch.utils.data.DataLoader(train_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
                 'test':torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers, shuffle = True),
                 'valid':torch.utils.data.DataLoader(valid_data, batch_size=batch_size, num_workers=num_workers, shuffle = True)}

(IMPLEMENTATION) Model Architecture

Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.

In [11]:
import torchvision.models as models
import torch.nn as nn
import torch.optim as optim

## TODO: Specify model architecture 
# Load the pretrained model from pytorch
model_transfer = models.vgg16(pretrained=True)

# print out the model structure
print(model_transfer)

# Freeze training for all "features" layers
for param in model_transfer.features.parameters():
    param.requires_grad = False
    
n_inputs = model_transfer.classifier[6].in_features

# add last linear layer (n_inputs -> 133 dog breeds)
# new layers automatically have requires_grad = True
last_layer = nn.Linear(n_inputs, 133)

model_transfer.classifier[6] = last_layer

# check to see that your last layer produces the expected number of outputs
print(model_transfer.classifier[6].in_features)
print(model_transfer.classifier[6].out_features)
print(model_transfer)

if use_cuda:
    model_transfer = model_transfer.cuda()

#save the model structure
torch.save(model_transfer.state_dict(), 'model_transfer.pt')
VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace)
    (2): Dropout(p=0.5)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace)
    (5): Dropout(p=0.5)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)
4096
133
VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace)
    (2): Dropout(p=0.5)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace)
    (5): Dropout(p=0.5)
    (6): Linear(in_features=4096, out_features=133, bias=True)
  )
)

Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.

Answer: Ensured that the input is of size 224, in line with what VGG needs Ensured that the output no. of classes matched the no. of breeds

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.

In [12]:
criterion_transfer = nn.CrossEntropyLoss()
optimizer_transfer = optim.SGD(model_transfer.classifier.parameters(), lr=0.001)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.

In [13]:
def transfer_train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):

    # initialize tracker for minimum validation loss
    valid_loss_min = np.Inf
   
    for epoch in range(1, n_epochs+1):
        # keep track of training and validation loss
        train_loss = 0.0
        valid_loss = 0.0
        ###################
        # train the model #
        ###################
        
        # model by default is set to train
        for batch_i, (data, target) in enumerate(loaders_transfer['train']):
            # move tensors to GPU if CUDA is available
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            # clear the gradients of all optimized variables
            optimizer_transfer.zero_grad()
            # forward pass: compute predicted outputs by passing inputs to the model
            output = model_transfer(data)
            # calculate the batch loss
            loss = criterion_transfer(output, target)
            # backward pass: compute gradient of the loss with respect to model parameters
            loss.backward()
            # perform a single optimization step (parameter update)
            optimizer_transfer.step()
            # update training loss 
            train_loss += loss.item()
        
        if batch_i % 20 == 19:    # print training loss every specified number of mini-batches
            print('Epoch %d, Batch %d loss: %.16f' %
                  (epoch, batch_i + 1, train_loss / 20))
            train_loss = 0.0
        
        ######################    
        # validate the model #
        ######################
        model_transfer.eval()
        for batch_i, (data, target) in enumerate(loaders_transfer['valid']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## update the average validation loss
            valid_loss = valid_loss + ((1 / (batch_i + 1)) * (loss.data - valid_loss))
            
        # print training/validation statistics 
        print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
            epoch, 
            train_loss,
            valid_loss
            ))
        
        ## TODO: save the model if validation loss has decreased
        if valid_loss <= valid_loss_min:
            print('Validation loss decreased --> ',
                 'Saving model ...'.format(valid_loss_min, 
                                           valid_loss))
            torch.save(model_transfer.state_dict(), 'model_transfer.pt')
            valid_loss_min = valid_loss
    return model_transfer
    

#model_transfer.load_state_dict(torch.load('model_transfer.pt'))
In [14]:
# train the model
transfer_train(50, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, 'model_transfer.pt')

# load the model that got the best validation accuracy
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
Epoch: 1 	Training Loss: 1575.152612 	Validation Loss: 4.563591
Validation loss decreased -->  Saving model ...
Epoch: 2 	Training Loss: 1333.376142 	Validation Loss: 3.550210
Validation loss decreased -->  Saving model ...
Epoch: 3 	Training Loss: 1071.949733 	Validation Loss: 2.628254
Validation loss decreased -->  Saving model ...
Epoch: 4 	Training Loss: 865.034543 	Validation Loss: 2.559816
Validation loss decreased -->  Saving model ...
Epoch: 5 	Training Loss: 758.521471 	Validation Loss: 1.898185
Validation loss decreased -->  Saving model ...
Epoch: 6 	Training Loss: 676.473389 	Validation Loss: 2.126837
Epoch: 7 	Training Loss: 634.373423 	Validation Loss: 2.401735
Epoch: 8 	Training Loss: 599.500583 	Validation Loss: 1.852424
Validation loss decreased -->  Saving model ...
Epoch: 9 	Training Loss: 581.778705 	Validation Loss: 1.399327
Validation loss decreased -->  Saving model ...
Epoch: 10 	Training Loss: 551.318223 	Validation Loss: 2.237746
Epoch: 11 	Training Loss: 529.555394 	Validation Loss: 1.395524
Validation loss decreased -->  Saving model ...
Epoch: 12 	Training Loss: 518.612652 	Validation Loss: 1.648001
Epoch: 13 	Training Loss: 511.924364 	Validation Loss: 1.871903
Epoch: 14 	Training Loss: 501.362139 	Validation Loss: 1.780390
Epoch: 15 	Training Loss: 493.526779 	Validation Loss: 1.720859
Epoch: 16 	Training Loss: 483.946297 	Validation Loss: 1.479420
Epoch: 17 	Training Loss: 465.099813 	Validation Loss: 1.263477
Validation loss decreased -->  Saving model ...
Epoch: 18 	Training Loss: 472.217398 	Validation Loss: 1.975338
Epoch: 19 	Training Loss: 470.975328 	Validation Loss: 1.583369
Epoch: 20 	Training Loss: 446.490656 	Validation Loss: 1.294803
Epoch: 21 	Training Loss: 449.999432 	Validation Loss: 1.388844
Epoch: 22 	Training Loss: 440.733858 	Validation Loss: 1.570691
Epoch: 23 	Training Loss: 430.339770 	Validation Loss: 0.961736
Validation loss decreased -->  Saving model ...
Epoch: 24 	Training Loss: 426.864773 	Validation Loss: 1.253538
Epoch: 25 	Training Loss: 436.384195 	Validation Loss: 1.625928
Epoch: 26 	Training Loss: 428.167846 	Validation Loss: 0.722350
Validation loss decreased -->  Saving model ...
Epoch: 27 	Training Loss: 424.867754 	Validation Loss: 1.151133
Epoch: 28 	Training Loss: 430.268951 	Validation Loss: 1.311228
Epoch: 29 	Training Loss: 408.005731 	Validation Loss: 1.294069
Epoch: 30 	Training Loss: 410.302730 	Validation Loss: 1.089170
Epoch: 31 	Training Loss: 404.042851 	Validation Loss: 1.305294
Epoch: 32 	Training Loss: 407.124022 	Validation Loss: 0.916230
Epoch: 33 	Training Loss: 411.815884 	Validation Loss: 0.677662
Validation loss decreased -->  Saving model ...
Epoch: 34 	Training Loss: 389.046477 	Validation Loss: 0.796861
Epoch: 35 	Training Loss: 399.646483 	Validation Loss: 0.850340
Epoch: 36 	Training Loss: 396.511407 	Validation Loss: 1.433793
Epoch: 37 	Training Loss: 385.954252 	Validation Loss: 1.874096
Epoch: 38 	Training Loss: 389.263138 	Validation Loss: 0.922395
Epoch: 39 	Training Loss: 377.209680 	Validation Loss: 1.147475
Epoch: 40 	Training Loss: 384.674570 	Validation Loss: 0.993289
Epoch: 41 	Training Loss: 378.096700 	Validation Loss: 1.542078
Epoch: 42 	Training Loss: 373.471380 	Validation Loss: 1.260321
Epoch: 43 	Training Loss: 363.737155 	Validation Loss: 0.756341
Epoch: 44 	Training Loss: 369.380604 	Validation Loss: 2.033163
Epoch: 45 	Training Loss: 371.480707 	Validation Loss: 1.469019
Epoch: 46 	Training Loss: 362.130770 	Validation Loss: 1.596555
Epoch: 47 	Training Loss: 374.579622 	Validation Loss: 0.739257
Epoch: 48 	Training Loss: 376.942871 	Validation Loss: 0.635814
Validation loss decreased -->  Saving model ...
Epoch: 49 	Training Loss: 362.047621 	Validation Loss: 1.363015
Epoch: 50 	Training Loss: 360.806547 	Validation Loss: 1.079504

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.

In [16]:
def test_transfer(loaders, model, criterion, use_cuda):

    # monitor test loss and accuracy
    test_loss = 0.
    correct = 0.
    total = 0.

    model_transfer.eval()
    for batch_i, (data, target) in enumerate(loaders_transfer['test']):
        # move to GPU
        if use_cuda:
            data, target = data.cuda(), target.cuda()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = model_transfer(data)
        # calculate the loss
        loss = criterion_transfer(output, target)
        # update average test loss 
        test_loss = test_loss + ((1 / (batch_i + 1)) * (loss.data - test_loss))
        # convert output probabilities to predicted class
        pred = output.data.max(1, keepdim=True)[1]
        # compare predictions to true label
        correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
        total += data.size(0)
            
    print('Test Loss: {:.6f}\n'.format(test_loss))

    print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))

# call test function    
test_transfer(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Test Loss: 1.426471


Test Accuracy: 60% (504/836)

(IMPLEMENTATION) Predict Dog Breed with the Model

Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.

In [17]:
### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.

from PIL import Image
ImageFile.LOAD_TRUNCATED_IMAGES = True
from torchvision import datasets, transforms


from PIL import Image
data = {"train" : train_data, "valid" : valid_data, "test" : test_data}
data_transfer = data
# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in data_transfer['train'].classes]

def predict_breed_transfer(img_path):
    # load the image and return the predicted breed
    img_transform = transforms.Compose([transforms.Resize((224,224)),
                                    transforms.ToTensor(),
                                    transforms.Normalize([0.485, 0.456, 0.406],
                                    [0.229, 0.224, 0.225])
                                    ])
    img = Image.open(img_path)
    img = img_transform(img).unsqueeze(0)
    if use_cuda:
        img = img.cuda()
    model_transfer.eval()
    output = model_transfer(img)
    prediction = output.argmax().item()
    breed_prediction = class_names[prediction]
    return breed_prediction

predict_breed_transfer('/data/dog_images/train/001.Affenpinscher/Affenpinscher_00001.jpg')
Out[17]:
'Affenpinscher'

Step 5: Write your Algorithm

Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,

  • if a dog is detected in the image, return the predicted breed.
  • if a human is detected in the image, return the resembling dog breed.
  • if neither is detected in the image, provide output that indicates an error.

You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and human_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.

Some sample output for our algorithm is provided below, but feel free to design your own user experience!

Sample Human Output

(IMPLEMENTATION) Write your Algorithm

In [62]:
### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.
import matplotlib.pyplot as plt                        
%matplotlib inline

def run_app(img_path):
    ## handle cases for a human face, dog, and neither
    img = Image.open(img_path)
    # display the image
    plt.imshow(img)
    plt.show()
    if dog_detector(img_path)==True:
        output = print('Dog breed detected:', predict_breed_transfer(img_path))

    elif face_detector(img_path)==True:
        output = print('Human detected: looks like a ...', predict_breed_transfer(img_path))

    else:
        output = print("Error - image is not a dog or a human")
    return output    

Step 6: Test Your Algorithm

In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?

(IMPLEMENTATION) Test Your Algorithm on Sample Images!

Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.

Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.

Answer:

I could use batch normalization to further improve the performance of the model. Increase the number of epochs, as we still see a decrease in validation loss after only 50. Increase the learning rate slightly to have model learn faster.

In [67]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.

import numpy as np

for file in np.hstack((human_files[0:25], dog_files[0:25])):
    run_app(file)
Human detected: looks like a ... Beagle
Human detected: looks like a ... Australian shepherd
Human detected: looks like a ... Poodle
Human detected: looks like a ... Ibizan hound
Human detected: looks like a ... Ibizan hound
Human detected: looks like a ... Poodle
Human detected: looks like a ... Welsh springer spaniel
Human detected: looks like a ... Australian shepherd
Human detected: looks like a ... Poodle
Human detected: looks like a ... Australian shepherd
Human detected: looks like a ... Poodle
Human detected: looks like a ... Poodle
Human detected: looks like a ... Lowchen
Human detected: looks like a ... Poodle
Human detected: looks like a ... Cavalier king charles spaniel
Human detected: looks like a ... Lowchen
Human detected: looks like a ... Bearded collie
Human detected: looks like a ... Ibizan hound
Human detected: looks like a ... Australian shepherd
Human detected: looks like a ... Alaskan malamute
Human detected: looks like a ... Cocker spaniel
Human detected: looks like a ... Havanese
Human detected: looks like a ... Silky terrier
Human detected: looks like a ... Ibizan hound
Human detected: looks like a ... Dogue de bordeaux
Dog breed detected: Bullmastiff
Dog breed detected: Bullmastiff
Error - image is not a dog or a human
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Cane corso
Error - image is not a dog or a human
Error - image is not a dog or a human
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Error - image is not a dog or a human
Error - image is not a dog or a human
Dog breed detected: Mastiff
Dog breed detected: Mastiff
Error - image is not a dog or a human